Structured Prompting and LLM Ensembling for Multimodal Conversational Aspect-based Sentiment Analysis

• URL: http://arxiv.org/abs/2512.22603v1
• Date: Sat, 27 Dec 2025 14:14:16 GMT
• Title: Structured Prompting and LLM Ensembling for Multimodal Conversational Aspect-based Sentiment Analysis
• Authors: Zhiqiang Gao, Shihao Gao, Zixing Zhang, Yihao Guo, Hongyu Chen, Jing Han,
• Abstract summary: TheMCABSA Challenge invited participants to tackle two demanding subtasks: (1) extracting a comprehensive sentiment sextuple, including holder, target, aspect, opinion, sentiment, and rationale from multi-speaker dialogues, and (2) detecting sentiment flipping, which detects dynamic sentiment shifts and their underlying triggers.<n>Our system achieved a 47.38% average score on Subtask-I and a 74.12% exact match F1 on Subtask-II, showing the effectiveness of step-wise refinement and ensemble strategies in rich, multimodal sentiment analysis tasks.
• Score: 18.617521594914546
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Understanding sentiment in multimodal conversations is a complex yet crucial challenge toward building emotionally intelligent AI systems. The Multimodal Conversational Aspect-based Sentiment Analysis (MCABSA) Challenge invited participants to tackle two demanding subtasks: (1) extracting a comprehensive sentiment sextuple, including holder, target, aspect, opinion, sentiment, and rationale from multi-speaker dialogues, and (2) detecting sentiment flipping, which detects dynamic sentiment shifts and their underlying triggers. For Subtask-I, in the present paper, we designed a structured prompting pipeline that guided large language models (LLMs) to sequentially extract sentiment components with refined contextual understanding. For Subtask-II, we further leveraged the complementary strengths of three LLMs through ensembling to robustly identify sentiment transitions and their triggers. Our system achieved a 47.38% average score on Subtask-I and a 74.12% exact match F1 on Subtask-II, showing the effectiveness of step-wise refinement and ensemble strategies in rich, multimodal sentiment analysis tasks.

Related papers

• AIMA at SemEval-2024 Task 3: Simple Yet Powerful Emotion Cause Pair Analysis [0.6465251961564605]
  The SemEval-2024 Task 3 presents two subtasks focusing on emotion-cause pair extraction within conversational contexts.<n>Subtask 1 revolves around the extraction of textual emotion-cause pairs, where causes are defined and annotated as textual spans within the conversation.<n>Subtask 2 extends the analysis to encompass multimodal cues, including language, audio, and vision, acknowledging instances where causes may not be exclusively represented in the textual data.
  arXiv  Detail & Related papers  (2025-01-19T21:16:31Z)
• PanoSent: A Panoptic Sextuple Extraction Benchmark for Multimodal Conversational Aspect-based Sentiment Analysis [74.41260927676747]
  This paper bridges the gaps by introducing a multimodal conversational Sentiment Analysis (ABSA) To benchmark the tasks, we construct PanoSent, a dataset annotated both manually and automatically, featuring high quality, large scale, multimodality, multilingualism, multi-scenarios, and covering both implicit and explicit sentiment elements. To effectively address the tasks, we devise a novel Chain-of-Sentiment reasoning framework, together with a novel multimodal large language model (namely Sentica) and a paraphrase-based verification mechanism.
  arXiv  Detail & Related papers  (2024-08-18T13:51:01Z)
• Large Language Models Meet Text-Centric Multimodal Sentiment Analysis: A Survey [66.166184609616]
  ChatGPT has opened up immense potential for applying large language models (LLMs) to text-centric multimodal tasks. It is still unclear how existing LLMs can adapt better to text-centric multimodal sentiment analysis tasks.
  arXiv  Detail & Related papers  (2024-06-12T10:36:27Z)
• SemEval-2024 Task 3: Multimodal Emotion Cause Analysis in Conversations [53.60993109543582]
  SemEval-2024 Task 3, named Multimodal Emotion Cause Analysis in Conversations, aims at extracting all pairs of emotions and their corresponding causes from conversations. Under different modality settings, it consists of two subtasks: Textual Emotion-Cause Pair Extraction in Conversations (TECPE) and Multimodal Emotion-Cause Pair Extraction in Conversations (MECPE) In this paper, we introduce the task, dataset and evaluation settings, summarize the systems of the top teams, and discuss the findings of the participants.
  arXiv  Detail & Related papers  (2024-05-19T09:59:00Z)
• Two in One Go: Single-stage Emotion Recognition with Decoupled Subject-context Transformer [78.35816158511523]
  We present a single-stage emotion recognition approach, employing a Decoupled Subject-Context Transformer (DSCT) for simultaneous subject localization and emotion classification. We evaluate our single-stage framework on two widely used context-aware emotion recognition datasets, CAER-S and EMOTIC.
  arXiv  Detail & Related papers  (2024-04-26T07:30:32Z)
• TCAN: Text-oriented Cross Attention Network for Multimodal Sentiment Analysis [26.867610944625337]
  Multimodal Sentiment Analysis (MSA) endeavors to understand human sentiment by leveraging language, visual, and acoustic modalities.<n>Past research predominantly focused on improving representation learning techniques and feature fusion strategies.<n>We introduce a Text-oriented Cross-Attention Network (TCAN) emphasizing the predominant role of the text modality in MSA.
  arXiv  Detail & Related papers  (2024-04-06T07:56:09Z)
• UniSA: Unified Generative Framework for Sentiment Analysis [48.78262926516856]
  Sentiment analysis aims to understand people's emotional states and predict emotional categories based on multimodal information. It consists of several subtasks, such as emotion recognition in conversation (ERC), aspect-based sentiment analysis (ABSA), and multimodal sentiment analysis (MSA)
  arXiv  Detail & Related papers  (2023-09-04T03:49:30Z)
• Dual Semantic Knowledge Composed Multimodal Dialog Systems [114.52730430047589]
  We propose a novel multimodal task-oriented dialog system named MDS-S2. It acquires the context related attribute and relation knowledge from the knowledge base. We also devise a set of latent query variables to distill the semantic information from the composed response representation.
  arXiv  Detail & Related papers  (2023-05-17T06:33:26Z)
• Bidirectional Machine Reading Comprehension for Aspect Sentiment Triplet Extraction [8.208671244754317]
  Aspect sentiment triplet extraction (ASTE) is an emerging task in fine-grained opinion mining. We transform ASTE task into a multi-turn machine reading comprehension (MTMRC) task. We propose a bidirectional MRC (BMRC) framework to address this challenge.
  arXiv  Detail & Related papers  (2021-03-13T09:30:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.